Machine Learning-Based Quantification of Lateral Flow Assay Using Smartphone-Captured Images
Lateral flow assay has been extensively used for at-home testing and point-of-care diagnostics in rural areas. Despite its advantages as convenient and low-cost testing, it suffers from poor quantification capacity where only yes/no or positive/negative diagnostics are achieved. In this study, machi...
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-01-01
|
| Series: | Biosensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2079-6374/15/1/19 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832588946365743104 |
|---|---|
| author | Anne M. Davis Asahi Tomitaka |
| author_facet | Anne M. Davis Asahi Tomitaka |
| author_sort | Anne M. Davis |
| collection | DOAJ |
| description | Lateral flow assay has been extensively used for at-home testing and point-of-care diagnostics in rural areas. Despite its advantages as convenient and low-cost testing, it suffers from poor quantification capacity where only yes/no or positive/negative diagnostics are achieved. In this study, machine learning and deep learning models were developed to quantify the analyte load from smartphone-captured images of the lateral flow assay test. The comparative analysis identified that random forest and convolutional neural network (CNN) models performed well in classifying the lateral flow assay results compared to other well-established machine learning models. When trained on small-size images, random forest models excelled CNN models in image classification. Contrarily, CNN models outperformed random forest models in classifying noisy images. |
| format | Article |
| id | doaj-art-f901d16580704b37ae93b870b6036867 |
| institution | Kabale University |
| issn | 2079-6374 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Biosensors |
| spelling | doaj-art-f901d16580704b37ae93b870b60368672025-01-24T13:25:27ZengMDPI AGBiosensors2079-63742025-01-011511910.3390/bios15010019Machine Learning-Based Quantification of Lateral Flow Assay Using Smartphone-Captured ImagesAnne M. Davis0Asahi Tomitaka1Department of Computer and Information Sciences, University of Houston-Victoria, Victoria, TX 77904, USADepartment of Computer and Information Sciences, University of Houston-Victoria, Victoria, TX 77904, USALateral flow assay has been extensively used for at-home testing and point-of-care diagnostics in rural areas. Despite its advantages as convenient and low-cost testing, it suffers from poor quantification capacity where only yes/no or positive/negative diagnostics are achieved. In this study, machine learning and deep learning models were developed to quantify the analyte load from smartphone-captured images of the lateral flow assay test. The comparative analysis identified that random forest and convolutional neural network (CNN) models performed well in classifying the lateral flow assay results compared to other well-established machine learning models. When trained on small-size images, random forest models excelled CNN models in image classification. Contrarily, CNN models outperformed random forest models in classifying noisy images.https://www.mdpi.com/2079-6374/15/1/19machine learningdeep learningCNNlateral flow assay |
| spellingShingle | Anne M. Davis Asahi Tomitaka Machine Learning-Based Quantification of Lateral Flow Assay Using Smartphone-Captured Images Biosensors machine learning deep learning CNN lateral flow assay |
| title | Machine Learning-Based Quantification of Lateral Flow Assay Using Smartphone-Captured Images |
| title_full | Machine Learning-Based Quantification of Lateral Flow Assay Using Smartphone-Captured Images |
| title_fullStr | Machine Learning-Based Quantification of Lateral Flow Assay Using Smartphone-Captured Images |
| title_full_unstemmed | Machine Learning-Based Quantification of Lateral Flow Assay Using Smartphone-Captured Images |
| title_short | Machine Learning-Based Quantification of Lateral Flow Assay Using Smartphone-Captured Images |
| title_sort | machine learning based quantification of lateral flow assay using smartphone captured images |
| topic | machine learning deep learning CNN lateral flow assay |
| url | https://www.mdpi.com/2079-6374/15/1/19 |
| work_keys_str_mv | AT annemdavis machinelearningbasedquantificationoflateralflowassayusingsmartphonecapturedimages AT asahitomitaka machinelearningbasedquantificationoflateralflowassayusingsmartphonecapturedimages |